Research Agenda

Research

My work connects spatial intelligence, agentic intelligence, and urban science through models, agents, benchmarks, and real-world systems.

Focus Areas

Spatial Intelligence

This direction studies how large language models, vision-language models, and urban world models can understand cities, geospatial data, street views, satellite images, maps, trajectories, and multimodal urban signals.

(M)LLMSpatial IntelligenceUrban Analytics
KDD 2026 D&B

UrbanWell: Benchmarking Multimodal Large Language Models for Spatio-Temporal Urban Wellbeing Analytics

Yanxin Xi, Xiang Su, Jie Feng, et al.

(M)LLMSpatial IntelligenceUrban Analytics
ICLR 2026

CityLens: Benchmarking Large Vision-Language Models for Urban Socioeconomic Sensing

Tianhui Liu, Hetian Pang, Xin Zhang, et al.

(M)LLMSpatial IntelligenceUrban Analytics
ICCV 2025

UrbanLLaVA: Multimodal LLM for Urban Intelligence

Jie Feng, Shengyuan Wang, Tianhui Liu, Yanxin Xi, Yong Li

Urban multimodal model for spatial reasoning and understanding.

(M)LLMSpatial IntelligenceUrban Analytics
KDD 2025 Research

CityGPT: Empowering Urban Spatial Cognition

Jie Feng, Tianhui Liu, Yuwei Du, et al.

Urban spatial cognition framework for large language models.

(M)LLMSpatial IntelligenceUrban Analytics

Agentic Intelligence

This direction builds LLM-powered agents and embodied agents that coordinate data processing, model planning, optimization, verification, and simulation for real-world applications.

AgentHuman BehaviorDecision Making
KDD 2026 AI4S

Designing A Scalable LLM Agent Framework for Large-scale Urban Segregation Simulation

Qingbin Zeng, Yuwei Yan, Zhiheng Zheng, et al.

AgentHuman BehaviorUrban Analytics
NeurIPS 2025

TrajAgent: LLM-Agent Framework for Trajectory Modeling

Yuwei Du, Jie Feng, Jie Zhao, Yong Li

LLM-agent framework for trajectory modeling.

AgentHuman Behavior
NAACL 2025

AgentMove: A Large Language Model based Agentic Framework for Zero-shot Next Location Prediction

Jie Feng, Yuwei Du, Jie Zhao, Yong Li

AgentHuman Behavior
ACL 2025 Findings

Open-Set Living Need Prediction with Large Language Models

Xiaochong Lan, Jie Feng, Yizhou Sun, et al.

AgentHuman Behavior

Urban Science

This direction focuses on urban analytics and principled modeling of human behavior and urban systems, including trajectory prediction, urban flow forecasting, spatiotemporal learning, and industrial-scale decision systems.

Urban AnalyticsHuman BehaviorTime Series
KDD 2024 Research

UniST: A Prompt-Empowered Universal Model for Urban Spatio-Temporal Prediction

Yuan Yuan, Jingtao Ding, Jie Feng, et al.

Time SeriesUrban Analytics
WWW 2018

DeepMove: Predicting Human Mobility with Attentional Recurrent Networks

Jie Feng, Yong Li, Chao Zhang, et al.

Human Behavior
ACM TKDD 2023

Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solution

Fuxian Li, Jie Feng, Huan Yan, et al.

Time SeriesUrban Analytics
AAAI 2019

DeepSTN+: Context-aware Spatial-Temporal Neural Network for Crowd Flow Prediction in Metropolis

Ziqian Lin, Jie Feng, Ziyang Lu, et al.

Time SeriesUrban Analytics